data_loader.py 文件源码

def _collate_fn(batch):
    def func(p):
        return p[0].size(1)

    longest_sample = max(batch, key=func)[0]
    freq_size = longest_sample.size(0)
    minibatch_size = len(batch)
    max_seqlength = longest_sample.size(1)
    inputs = torch.zeros(minibatch_size, 1, freq_size, max_seqlength)
    input_percentages = torch.FloatTensor(minibatch_size)
    target_sizes = torch.IntTensor(minibatch_size)
    targets = []
    for x in range(minibatch_size):
        sample = batch[x]
        tensor = sample[0]
        target = sample[1]
        seq_length = tensor.size(1)
        inputs[x][0].narrow(1, 0, seq_length).copy_(tensor)
        input_percentages[x] = seq_length / float(max_seqlength)
        target_sizes[x] = len(target)
        targets.extend(target)
    targets = torch.IntTensor(targets)
    return inputs, targets, input_percentages, target_sizes